cleanup-cache
Clean system caches (npm, Homebrew, Yarn, browsers, Python/ML) to free disk space
Team lunch orchestration via DoorDash CLI - build a group round, emit checkout with split table, track payer rotation
$ npx -y skills add davila7/claude-code-templates --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/doordash-lunchContext preview
What this command does when you run it.
Team lunch orchestration via DoorDash CLI - build a group round, emit checkout with split table, track payer rotation
allowed-tools: Bash(dd-cli:*), Bash(cat:*), Bash(jq:*), Bash(mkdir:*), Read, Write, Edit argument-hint: [order | checkout | whose-turn | roster] description: Team lunch orchestration via DoorDash CLI - build a group round, emit checkout with split table, track payer rotation
Group order operation: **$ARGUMENTS**
Works with the `doordash-group-orders` skill (install it alongside — it defines the full flows; this command is the quick entrypoint). State: `team-food.json` (roster), `.dd/round-<date>.json` (active round), `.dd/rounds.jsonl` (history).
Parse `$ARGUMENTS`:
Run Flow 1 of the doordash-group-orders skill: roster check → constraint-aware restaurant shortlist via `dd-cli search` → per-member choices (favorites first, one question max per member) → build cart recording person → cart-item-id in the round ledger → show the cart grouped by person.
If the user pastes a thread of requests, parse it (Flow 2) instead of interviewing members.
1. Show the grouped cart one final time (per-person subtotals). 2. Emit the checkout URL — via `bash .claude/skills/doordash-spend-guard/scripts/dd-guard.sh checkout <cart-uuid>` when doordash-spend-guard is installed, otherwise `dd-cli order checkout-url --cart-uuid <cart-uuid>`. 3. Print a share-ready split table (markdown, ready to paste into Slack): person, items, subtotal share. 4. After the human confirms payment: pull order_uuid from `dd-cli order history`, ask who paid, append `{date, order_uuid, payer, split}` to `.dd/rounds.jsonl`, and offer the fee-proration fallback ("tell me the final total and I'll prorate the difference").
Read `.dd/rounds.jsonl`, compute per-member (consumed − paid) balances, name the next payer, show the balance table so the answer explains itself.
Show/edit `team-food.json` interactively: add/remove members, update hard constraints, allergens (ask severity explicitly), favorites, dislikes. Confirm the final JSON before writing.
split table footer.
Ready-to-use configurations for Anthropic's Claude Code. A comprehensive collection of AI agents, custom commands, settings, hooks, external integrations (MCPs), and project templates to enhance your development workflow.
Repo: davila7/claude-code-templates
Clean system caches (npm, Homebrew, Yarn, browsers, Python/ML) to free disk space
Create an SEO-optimized blog article for a Claude Code component with AI-generated cover image